© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 20283
    Prev
    Next
    INDEX
    Explanations

    measurements or quantities, particularly involving cups

    oai_token-act-pair · gpt-3.5-turbo

    references to containers, specifically 'cups'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Investigative
    -0.72
     mutation
    -0.70
    neg
    -0.69
     Cheney
    -0.68
     Hunter
    -0.66
     Hunt
    -0.65
     Wyoming
    -0.65
    ]]
    -0.64
    anthrop
    -0.63
     Investig
    -0.63
    POSITIVE LOGITS
     cups
    3.85
     Cups
    2.56
     cup
    2.39
     bowls
    1.78
    cup
    1.69
     teaspoons
    1.60
     Cup
    1.58
     tablespoons
    1.54
     cans
    1.52
     bottles
    1.52
    Activations Density 0.013%

    No Known Activations